PCA analysis of incorrect output

Question

What is sample data:

structure(c(368113, 87747.35, 508620.5, 370570.5, 87286.5, 612728, 
55029, 358521, 2802880, 2045399.5, 177099, 317974.5, 320687.95, 
6971292.55, 78949, 245415.95, 50148.5, 67992.5, 97634, 56139.5, 
371719.2, 80182.7, 612078.5, 367822.5, 80691, 665190.65, 28283.5, 
309720, 2853241.5, 1584324, 135482.5, 270959, 343879.1, 6748208.5, 
71534.9, 258976, 28911.75, 78306, 56358.7, 46783.5, 320882.85, 
53098.3, 537383.5, 404505.5, 89759.7, 624120.55, 40406, 258183.5, 
3144610.45, 1735583.5, 122013.5, 249741, 362585.35, 5383869.15, 
23172.2, 223704.45, 40543.7, 68522.5, 43187.05, 29745, 356058.5, 
89287.25, 492242.5, 452135.5, 97253.55, 575661.95, 65739.5, 334703.5, 
3136065, 1622936.5, 131381.5, 254362, 311496.3, 5627561, 68210.6, 
264610.1, 45851, 65010.5, 32665.5, 39957.5, 362476.75, 59451.65, 
548279, 345096.5, 93363.5, 596444.2, 11052.5, 252812, 2934035, 
1732707.55, 208409.5, 208076.5, 437764.25, 16195882.45, 77461.25, 
205803.85, 30437.5, 75540, 49576.75, 48878, 340380.5, 43785.35, 
482713, 340315, 64308.5, 517859.85, 11297, 268993.5, 3069028.5, 
1571889, 157561, 217596.5, 400610.65, 5703337.6, 50640.65, 197477.75, 
40070, 66619, 81564.55, 41436.5, 367592.3, 64954.9, 530093, 432025, 
87212.5, 553901.65, 20803.5, 333940.5, 3027254.5, 1494468, 195221, 
222895.5, 494429.45, 7706885.75, 60633.35, 192827.1, 29857.5, 
81001.5, 112588.65, 68904.5, 338822.5, 56868.15, 467350, 314526.5, 
105568, 749456.1, 19597.5, 298939.5, 2993199.2, 1615231.5, 229185.5, 
280433.5, 360156.15, 5254889.1, 79369.5, 175434.05, 40907.05, 
70919, 65720.15, 53054.5), .Dim = c(20L, 8L), .Dimnames = list(
    c("Anne", "Greg", "thomas", "Chris", "Gerard", "Monk", "Mart", 
    "Mutr", "Aeqe", "Tor", "Gaer", "Toaq", "Kolr", "Wera", "Home", 
    "Terlo", "Kulte", "Mercia", "Loki", "Herta"), c("Day_Rep1", 
    "Day_Rep2", "Day_Rep3", "Day_Rep4", "Day2_Rep1", "Day2_Rep2", 
    "Day2_Rep3", "Day2_Rep4")))

I would like to do a good PCA analysis. I expect the repetitions from Day to be well correlated with each other and to be repeated along with Day2 together. I tried to do some analysis using the following code:

## log transform
data_log <- log(data[, 1:8])
#vec_EOD_EON
dt_PCA <- prcomp(data_log,
                           center = TRUE,
                           scale. = TRUE)

library(devtools)
install_github("ggbiplot", "vqv")

library(ggbiplot)
g <- ggbiplot(dt_PCA, obs.scale = 1, var.scale = 1, 
              groups = colnames(dt_PCA), ellipse = TRUE, 
              circle = TRUE)
g <- g + scale_color_discrete(name = "")
g <- g + theme(legend.direction = 'horizontal', 
               legend.position = 'top')
print(g)

However, the output is not what I am looking for:

but I'm looking for something like this:

I would like to use dots for each row in the data and different colors for each of the replicas. It would be great to use similar colors for Day replicas, as well as for Day2.

Received data using ggplot:

Answer 1

Suppose you saved your data in df.

library(ggplot2)
pc_df <- prcomp(t(df), scale.=TRUE)
pc_table <- as.data.frame(pc_df$x[,1:2]) # extracting 1st and 2nd component

experiment_regex <- '(^[^_]+)_Rep(\\d+)' # extracting replicate and condition from your experiment names
pc_table$replicate <- as.factor(sub(experiment_regex,'\\2', rownames(pc_table)))
pc_table$condition <- as.factor(sub(experiment_regex,'\\1', rownames(pc_table)))

ggplot(pc_table, aes(PC1, PC2, color=condition, shape=replicate)) +
  geom_point() +
  xlab(sprintf('PC1 - %.1f%%', # extracting the percentage of each PC and print it on the axes
               summary(pc_df)$importance[2,1] * 100)) +
  ylab(sprintf('PC2 - %.1f%%', 
               summary(pc_df)$importance[2,2] * 100))

, , , - t(). , , .

, , ggplot2.

:

. , . 1 2 , 3 4. , ( 49%, 20%). , !